Heating, ventilation, and air conditioning (HVAC) systems account for up to 40% of the total energy consumption in buildings. Improving the modeling of HVAC components is necessary to optimize energy efficiency, maintain indoor thermal comfort, and reduce their carbon footprint. This work addresses the lack of a general methodology for data preprocessing by introducing a novel approach for feature extraction and feature selection based on physical equations and expert knowledge that can be applied to any data-driven model. The proposed framework enables the forecasting of indoor temperatures and the energy consumption of individual HVAC components. The methodology is validated with real-world data from a system involving a fan coil unit and a thermal inertia deposit powered by geothermal energy, achieving a coefficient of determination (R2) of 0.98 and mean absolute percentage error (MAPE) of 0.44%.